slack-user-mcp
Model Context Protocol server for authorized Slack workspace automation
Documentation
Slack User MCP Server
MCP Server for the Slack API, enabling Claude to interact with Slack workspaces as a user.
Tools
1. `slack_list_channels`
2. `slack_post_message`
3. `slack_reply_to_thread`
4. `slack_add_reaction`
5. `slack_get_channel_history`
6. `slack_get_thread_replies`
7. `slack_get_users`
8. `slack_get_user_profile`
Setup
1. Create a Slack App:
2. Configure User Token Scopes:
Navigate to "OAuth & Permissions" and add these scopes:
3. Install App to Workspace:
4. For organization-level tokens, get your Team ID (starts with a `T`) by following this guidance. It is optional for ordinary workspace tokens.
Treat OAuth tokens as secrets. Do not commit them, put them in issues or pull requests, or paste them into shared configuration. Rotate a token immediately if it is exposed.
Usage with Claude Desktop
Add the following to your `claude_desktop_config.json`:
Local Installation
First install and build the server:
git clone https://github.com/lars-hagen/slack-user-mcp.git
cd slack-user-mcp
npm install
npm run buildThen configure Claude Desktop:
{
"mcpServers": {
"slack": {
"command": "npm",
"args": [
"run",
"--prefix",
"/path/to/slack-user-mcp",
"start"
],
"env": {
"SLACK_TOKEN": "xoxp-your-user-token"
}
}
}
}NPX
This project is not published to npm. Do not use an `npx` package name for it. Clone and build it locally as shown above, then use the local configuration.
Docker
{
"mcpServers": {
"slack": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"SLACK_TOKEN",
"slack-user-mcp"
],
"env": {
"SLACK_TOKEN": "xoxp-your-user-token"
}
}
}
}Build the image first with `docker build -t slack-user-mcp .`. Add `-e SLACK_TEAM_ID` and `SLACK_TEAM_ID` to `env` only when using an organization-level token.
Installing via Smithery
To install Slack User Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @lars-hagen/slack-user-mcp --client claudeTroubleshooting
If you encounter permission errors, verify that:
1. All required scopes are added to your Slack app
2. The app is properly installed to your workspace
3. The token and, when needed, workspace ID are correctly copied to your configuration
4. The app has been added to the channels it needs to access
5. You're using a User OAuth Token (starts with `xoxp-`) rather than a Bot Token
Build
Docker build:
docker build -t slack-user-mcp .Maintenance status
This project receives focused, best-effort maintenance. It has no support SLA. Please report security concerns privately as described in SECURITY.md.
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Frequently asked questions
What is slack-user-mcp?
slack-user-mcp is Model Context Protocol server for authorized Slack workspace automation
How do I install slack-user-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is slack-user-mcp open source?
Yes — it is hosted on GitHub at https://github.com/lars-hagen/slack-user-mcp and has 11 stars.
Related MCP tools
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or API tokens.
CTTF: MCP integration between Cursor and Figma, allowing Cursor Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients. JavaScript-based implementation.
A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3.7, Claude Fable 5, Claude Opus 5, DeepSeek V4, Grok, OpenRouter, Kimi k3, GLM 5.3, SiliconFlow, GPT-oss, Gemma 4, Qwen 3.8
Connect your browser to AI models. Just use Dia on Chrome, Arc or Firefox.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP